Research Engineer, Agentic Systems

Ramp
•$204,400 - $352,000

About The Position

Ramp Labs, Ramp's AI research and engineering group, post-trains models on finance work, develops the environments and evaluations they learn from, and ships them into products used by more than 85,000 companies. The Research Engineer, Agentic Systems will design and operate systems that coordinate large numbers of agents across broad search spaces. These systems collect partial results from many agents and orchestrate them into useful outputs, such as merged pull requests, datasets, or inputs to other systems. The role covers the full lifecycle from prototype to production. It involves deciding how to decompose work, configure agents and models, coordinate and verify results, and control cost and latency. The engineer will also measure output quality at scale and turn successful experiments into reusable workflows on Ramp's existing orchestration stack.

Requirements

  • Experience building applied AI systems and LLM applications that have shipped.
  • Hands-on experience with multi-agent or high-fan-out LLM workloads, such as parallel agents, map-reduce over models, or large batch inference.
  • Strong Python engineering skills and experience building concurrent, distributed systems that hold up in production.
  • Ability to define the desired output before scaling an agent swarm and distinguish useful signal from agent noise.
  • Habit of measuring cost, yield, false-positive rate, and whether changes improve results.
  • Ability to own a roadmap and production system with little oversight.
  • Clear written communication.

Nice To Haves

  • Experience building agent orchestration or job systems such as Ray, Temporal, Modal, or custom systems.
  • Experience using LLMs to search large spaces, such as codebases, document sets, logs, or other large corpora.
  • Experience post-training or hosting open-source models for high-volume inference.
  • Background in distributed systems.
  • Public work to review, such as an agent framework, open-source project, write-up, or paper.

Responsibilities

  • Decide how to decompose work, what information each agent receives, how many agents to run, and which model to use for each step.
  • Improve model accuracy through context design, self-verification, voting, consensus across agents, and determining when additional agents no longer help.
  • Measure quality without reading every trace by using sampling, automated verification, and precision and recall on final outputs.
  • Reduce cost and latency per useful result through model routing, caching, early stopping, and smaller or fine-tuned models where effective.
  • Turn one-off experiments into reusable workflows on the existing orchestration stack.
  • Evaluate new models, inference setups, and training approaches, and incorporate effective options.
  • Own agentic systems from prototype through production.

Benefits

  • Flexible PTO.
  • Centralized home-office equipment ordering.
  • Health and wellness stipend.
  • Budget for intra-office travel.
  • Weekly coffee stipend.
  • United States: 100% medical, dental, and vision insurance coverage for the employee, with partial coverage for dependents.
  • United States: One Medical annual membership.
  • United States: 401(k) with employer match on contributions made while employed by Ramp.
  • United States: Fertility HRA of up to $10,000 per year.
  • United States: Parental leave of up to 16 weeks (birthing and bonding) or 8 weeks (bonding only) at 100% pay.
  • United States: Pet insurance.
  • United States: In-office lunch, snacks, drinks, and other perks.
  • United States: Relocation expense coverage to New York City or San Francisco, if needed.
  • Canada: Group medical, dental, and vision coverage through Sun Life.
  • Canada: Life, AD&D, and disability coverage.
  • Canada: Fertility drug coverage of up to $4,000 lifetime.
  • Canada: Group Retirement Plan with employer match (RRSP + DPSP).
  • Canada: Parental leave of up to 16 weeks (birthing and bonding) or 8 weeks (bonding only) at 100% pay, with additional time available at reduced pay.
  • Canada: Employee Assistance Program and virtual care through Lumino Health.
  • United Kingdom: Private medical insurance through Freedom Elite.
  • United Kingdom: Virtual GP and at-home care via eMed x Livi.
  • United Kingdom: Workplace pension through Penfold, with salary sacrifice option.
  • United Kingdom: Parental leave of up to 16 weeks (birthing and bonding) or 8 weeks (bonding only) at 100% pay, with additional time available at reduced pay.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service